INDEX

Explanations

phrases and terms associated with actions and activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilder

-0.40

 appréci

-0.38

 zasi

-0.36

berater

-0.35

 Reiche

-0.35

HostException

-0.35

 unggul

-0.35

-0.34

 scraped

-0.34

devServer

-0.34

POSITIVE LOGITS

 actions

0.94

 Actions

0.90

 activities

0.90

Activities

0.86

activities

0.84

 activity

0.84

 Activities

0.82

 ACTIVITIES

0.80

 ACTIVITY

0.79

Actions

0.77

Activations Density 0.532%

phrases and terms associated with actions and activities

No Comments

No Known Activations